diff --git a/models/audio_encoders/put_audio_encoder_models_here b/models/audio_encoders/put_audio_encoder_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/checkpoints/put_checkpoints_here b/models/checkpoints/put_checkpoints_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/checkpoints/sd_xl_turbo_1.0_fp16.safetensors b/models/checkpoints/sd_xl_turbo_1.0_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc5009cfdd6444d8d9f8557efca5b582054ec77d --- /dev/null +++ b/models/checkpoints/sd_xl_turbo_1.0_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e869ac7d6942cb327d68d5ed83a40447aadf20e0c3358d98b2cc9e270db0da26 +size 6938081905 diff --git a/models/checkpoints/v1-5-pruned-emaonly-fp16.safetensors b/models/checkpoints/v1-5-pruned-emaonly-fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2b9f5265289c9cc66100187c4db39636dd376122 --- /dev/null +++ b/models/checkpoints/v1-5-pruned-emaonly-fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9476a13728cd75d8279f6ec8bad753a66a1957ca375a1464dc63b37db6e3916 +size 2132696762 diff --git a/models/clip/put_clip_or_text_encoder_models_here b/models/clip/put_clip_or_text_encoder_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/clip_vision/clip_vision_h.safetensors b/models/clip_vision/clip_vision_h.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0451a9fda3873d0db8725fcea14e5660e1793f83 --- /dev/null +++ b/models/clip_vision/clip_vision_h.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64a7ef761bfccbadbaa3da77366aac4185a6c58fa5de5f589b42a65bcc21f161 +size 1264219396 diff --git a/models/clip_vision/put_clip_vision_models_here b/models/clip_vision/put_clip_vision_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/configs/anything_v3.yaml b/models/configs/anything_v3.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8bcfe584ae73d60e2c7a6f89b3f7befbd487ea34 --- /dev/null +++ b/models/configs/anything_v3.yaml @@ -0,0 +1,73 @@ +model: + base_learning_rate: 1.0e-04 + target: ldm.models.diffusion.ddpm.LatentDiffusion + params: + linear_start: 0.00085 + linear_end: 0.0120 + num_timesteps_cond: 1 + log_every_t: 200 + timesteps: 1000 + first_stage_key: "jpg" + cond_stage_key: "txt" + image_size: 64 + channels: 4 + cond_stage_trainable: false # Note: different from the one we trained before + conditioning_key: crossattn + monitor: val/loss_simple_ema + scale_factor: 0.18215 + use_ema: False + + scheduler_config: # 10000 warmup steps + target: ldm.lr_scheduler.LambdaLinearScheduler + params: + warm_up_steps: [ 10000 ] + cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases + f_start: [ 1.e-6 ] + f_max: [ 1. ] + f_min: [ 1. ] + + unet_config: + target: ldm.modules.diffusionmodules.openaimodel.UNetModel + params: + image_size: 32 # unused + in_channels: 4 + out_channels: 4 + model_channels: 320 + attention_resolutions: [ 4, 2, 1 ] + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 4 ] + num_heads: 8 + use_spatial_transformer: True + transformer_depth: 1 + context_dim: 768 + use_checkpoint: True + legacy: False + + first_stage_config: + target: ldm.models.autoencoder.AutoencoderKL + params: + embed_dim: 4 + monitor: val/rec_loss + ddconfig: + double_z: true + z_channels: 4 + resolution: 256 + in_channels: 3 + out_ch: 3 + ch: 128 + ch_mult: + - 1 + - 2 + - 4 + - 4 + num_res_blocks: 2 + attn_resolutions: [] + dropout: 0.0 + lossconfig: + target: torch.nn.Identity + + cond_stage_config: + target: ldm.modules.encoders.modules.FrozenCLIPEmbedder + params: + layer: "hidden" + layer_idx: -2 diff --git a/models/configs/v1-inference.yaml b/models/configs/v1-inference.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d4effe569e897369918625f9d8be5603a0e6a0d6 --- /dev/null +++ b/models/configs/v1-inference.yaml @@ -0,0 +1,70 @@ +model: + base_learning_rate: 1.0e-04 + target: ldm.models.diffusion.ddpm.LatentDiffusion + params: + linear_start: 0.00085 + linear_end: 0.0120 + num_timesteps_cond: 1 + log_every_t: 200 + timesteps: 1000 + first_stage_key: "jpg" + cond_stage_key: "txt" + image_size: 64 + channels: 4 + cond_stage_trainable: false # Note: different from the one we trained before + conditioning_key: crossattn + monitor: val/loss_simple_ema + scale_factor: 0.18215 + use_ema: False + + scheduler_config: # 10000 warmup steps + target: ldm.lr_scheduler.LambdaLinearScheduler + params: + warm_up_steps: [ 10000 ] + cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases + f_start: [ 1.e-6 ] + f_max: [ 1. ] + f_min: [ 1. ] + + unet_config: + target: ldm.modules.diffusionmodules.openaimodel.UNetModel + params: + image_size: 32 # unused + in_channels: 4 + out_channels: 4 + model_channels: 320 + attention_resolutions: [ 4, 2, 1 ] + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 4 ] + num_heads: 8 + use_spatial_transformer: True + transformer_depth: 1 + context_dim: 768 + use_checkpoint: True + legacy: False + + first_stage_config: + target: ldm.models.autoencoder.AutoencoderKL + params: + embed_dim: 4 + monitor: val/rec_loss + ddconfig: + double_z: true + z_channels: 4 + resolution: 256 + in_channels: 3 + out_ch: 3 + ch: 128 + ch_mult: + - 1 + - 2 + - 4 + - 4 + num_res_blocks: 2 + attn_resolutions: [] + dropout: 0.0 + lossconfig: + target: torch.nn.Identity + + cond_stage_config: + target: ldm.modules.encoders.modules.FrozenCLIPEmbedder diff --git a/models/configs/v1-inference_clip_skip_2.yaml b/models/configs/v1-inference_clip_skip_2.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8bcfe584ae73d60e2c7a6f89b3f7befbd487ea34 --- /dev/null +++ b/models/configs/v1-inference_clip_skip_2.yaml @@ -0,0 +1,73 @@ +model: + base_learning_rate: 1.0e-04 + target: ldm.models.diffusion.ddpm.LatentDiffusion + params: + linear_start: 0.00085 + linear_end: 0.0120 + num_timesteps_cond: 1 + log_every_t: 200 + timesteps: 1000 + first_stage_key: "jpg" + cond_stage_key: "txt" + image_size: 64 + channels: 4 + cond_stage_trainable: false # Note: different from the one we trained before + conditioning_key: crossattn + monitor: val/loss_simple_ema + scale_factor: 0.18215 + use_ema: False + + scheduler_config: # 10000 warmup steps + target: ldm.lr_scheduler.LambdaLinearScheduler + params: + warm_up_steps: [ 10000 ] + cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases + f_start: [ 1.e-6 ] + f_max: [ 1. ] + f_min: [ 1. ] + + unet_config: + target: ldm.modules.diffusionmodules.openaimodel.UNetModel + params: + image_size: 32 # unused + in_channels: 4 + out_channels: 4 + model_channels: 320 + attention_resolutions: [ 4, 2, 1 ] + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 4 ] + num_heads: 8 + use_spatial_transformer: True + transformer_depth: 1 + context_dim: 768 + use_checkpoint: True + legacy: False + + first_stage_config: + target: ldm.models.autoencoder.AutoencoderKL + params: + embed_dim: 4 + monitor: val/rec_loss + ddconfig: + double_z: true + z_channels: 4 + resolution: 256 + in_channels: 3 + out_ch: 3 + ch: 128 + ch_mult: + - 1 + - 2 + - 4 + - 4 + num_res_blocks: 2 + attn_resolutions: [] + dropout: 0.0 + lossconfig: + target: torch.nn.Identity + + cond_stage_config: + target: ldm.modules.encoders.modules.FrozenCLIPEmbedder + params: + layer: "hidden" + layer_idx: -2 diff --git a/models/configs/v1-inference_clip_skip_2_fp16.yaml b/models/configs/v1-inference_clip_skip_2_fp16.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7eca31c7b5e571c2b1348e94ed9d69978ebd2d52 --- /dev/null +++ b/models/configs/v1-inference_clip_skip_2_fp16.yaml @@ -0,0 +1,74 @@ +model: + base_learning_rate: 1.0e-04 + target: ldm.models.diffusion.ddpm.LatentDiffusion + params: + linear_start: 0.00085 + linear_end: 0.0120 + num_timesteps_cond: 1 + log_every_t: 200 + timesteps: 1000 + first_stage_key: "jpg" + cond_stage_key: "txt" + image_size: 64 + channels: 4 + cond_stage_trainable: false # Note: different from the one we trained before + conditioning_key: crossattn + monitor: val/loss_simple_ema + scale_factor: 0.18215 + use_ema: False + + scheduler_config: # 10000 warmup steps + target: ldm.lr_scheduler.LambdaLinearScheduler + params: + warm_up_steps: [ 10000 ] + cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases + f_start: [ 1.e-6 ] + f_max: [ 1. ] + f_min: [ 1. ] + + unet_config: + target: ldm.modules.diffusionmodules.openaimodel.UNetModel + params: + use_fp16: True + image_size: 32 # unused + in_channels: 4 + out_channels: 4 + model_channels: 320 + attention_resolutions: [ 4, 2, 1 ] + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 4 ] + num_heads: 8 + use_spatial_transformer: True + transformer_depth: 1 + context_dim: 768 + use_checkpoint: True + legacy: False + + first_stage_config: + target: ldm.models.autoencoder.AutoencoderKL + params: + embed_dim: 4 + monitor: val/rec_loss + ddconfig: + double_z: true + z_channels: 4 + resolution: 256 + in_channels: 3 + out_ch: 3 + ch: 128 + ch_mult: + - 1 + - 2 + - 4 + - 4 + num_res_blocks: 2 + attn_resolutions: [] + dropout: 0.0 + lossconfig: + target: torch.nn.Identity + + cond_stage_config: + target: ldm.modules.encoders.modules.FrozenCLIPEmbedder + params: + layer: "hidden" + layer_idx: -2 diff --git a/models/configs/v1-inference_fp16.yaml b/models/configs/v1-inference_fp16.yaml new file mode 100644 index 0000000000000000000000000000000000000000..147f42b17b835cc839338156f99e8f971df5c1aa --- /dev/null +++ b/models/configs/v1-inference_fp16.yaml @@ -0,0 +1,71 @@ +model: + base_learning_rate: 1.0e-04 + target: ldm.models.diffusion.ddpm.LatentDiffusion + params: + linear_start: 0.00085 + linear_end: 0.0120 + num_timesteps_cond: 1 + log_every_t: 200 + timesteps: 1000 + first_stage_key: "jpg" + cond_stage_key: "txt" + image_size: 64 + channels: 4 + cond_stage_trainable: false # Note: different from the one we trained before + conditioning_key: crossattn + monitor: val/loss_simple_ema + scale_factor: 0.18215 + use_ema: False + + scheduler_config: # 10000 warmup steps + target: ldm.lr_scheduler.LambdaLinearScheduler + params: + warm_up_steps: [ 10000 ] + cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases + f_start: [ 1.e-6 ] + f_max: [ 1. ] + f_min: [ 1. ] + + unet_config: + target: ldm.modules.diffusionmodules.openaimodel.UNetModel + params: + use_fp16: True + image_size: 32 # unused + in_channels: 4 + out_channels: 4 + model_channels: 320 + attention_resolutions: [ 4, 2, 1 ] + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 4 ] + num_heads: 8 + use_spatial_transformer: True + transformer_depth: 1 + context_dim: 768 + use_checkpoint: True + legacy: False + + first_stage_config: + target: ldm.models.autoencoder.AutoencoderKL + params: + embed_dim: 4 + monitor: val/rec_loss + ddconfig: + double_z: true + z_channels: 4 + resolution: 256 + in_channels: 3 + out_ch: 3 + ch: 128 + ch_mult: + - 1 + - 2 + - 4 + - 4 + num_res_blocks: 2 + attn_resolutions: [] + dropout: 0.0 + lossconfig: + target: torch.nn.Identity + + cond_stage_config: + target: ldm.modules.encoders.modules.FrozenCLIPEmbedder diff --git a/models/configs/v1-inpainting-inference.yaml b/models/configs/v1-inpainting-inference.yaml new file mode 100644 index 0000000000000000000000000000000000000000..45f3f82d461cd8c6109f26ec3b1da75366eda0b0 --- /dev/null +++ b/models/configs/v1-inpainting-inference.yaml @@ -0,0 +1,71 @@ +model: + base_learning_rate: 7.5e-05 + target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion + params: + linear_start: 0.00085 + linear_end: 0.0120 + num_timesteps_cond: 1 + log_every_t: 200 + timesteps: 1000 + first_stage_key: "jpg" + cond_stage_key: "txt" + image_size: 64 + channels: 4 + cond_stage_trainable: false # Note: different from the one we trained before + conditioning_key: hybrid # important + monitor: val/loss_simple_ema + scale_factor: 0.18215 + finetune_keys: null + + scheduler_config: # 10000 warmup steps + target: ldm.lr_scheduler.LambdaLinearScheduler + params: + warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch + cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases + f_start: [ 1.e-6 ] + f_max: [ 1. ] + f_min: [ 1. ] + + unet_config: + target: ldm.modules.diffusionmodules.openaimodel.UNetModel + params: + image_size: 32 # unused + in_channels: 9 # 4 data + 4 downscaled image + 1 mask + out_channels: 4 + model_channels: 320 + attention_resolutions: [ 4, 2, 1 ] + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 4 ] + num_heads: 8 + use_spatial_transformer: True + transformer_depth: 1 + context_dim: 768 + use_checkpoint: True + legacy: False + + first_stage_config: + target: ldm.models.autoencoder.AutoencoderKL + params: + embed_dim: 4 + monitor: val/rec_loss + ddconfig: + double_z: true + z_channels: 4 + resolution: 256 + in_channels: 3 + out_ch: 3 + ch: 128 + ch_mult: + - 1 + - 2 + - 4 + - 4 + num_res_blocks: 2 + attn_resolutions: [] + dropout: 0.0 + lossconfig: + target: torch.nn.Identity + + cond_stage_config: + target: ldm.modules.encoders.modules.FrozenCLIPEmbedder + diff --git a/models/configs/v2-inference-v.yaml b/models/configs/v2-inference-v.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8ec8dfbfefe94ae8522c93017668fea78d580acf --- /dev/null +++ b/models/configs/v2-inference-v.yaml @@ -0,0 +1,68 @@ +model: + base_learning_rate: 1.0e-4 + target: ldm.models.diffusion.ddpm.LatentDiffusion + params: + parameterization: "v" + linear_start: 0.00085 + linear_end: 0.0120 + num_timesteps_cond: 1 + log_every_t: 200 + timesteps: 1000 + first_stage_key: "jpg" + cond_stage_key: "txt" + image_size: 64 + channels: 4 + cond_stage_trainable: false + conditioning_key: crossattn + monitor: val/loss_simple_ema + scale_factor: 0.18215 + use_ema: False # we set this to false because this is an inference only config + + unet_config: + target: ldm.modules.diffusionmodules.openaimodel.UNetModel + params: + use_checkpoint: True + use_fp16: True + image_size: 32 # unused + in_channels: 4 + out_channels: 4 + model_channels: 320 + attention_resolutions: [ 4, 2, 1 ] + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 4 ] + num_head_channels: 64 # need to fix for flash-attn + use_spatial_transformer: True + use_linear_in_transformer: True + transformer_depth: 1 + context_dim: 1024 + legacy: False + + first_stage_config: + target: ldm.models.autoencoder.AutoencoderKL + params: + embed_dim: 4 + monitor: val/rec_loss + ddconfig: + #attn_type: "vanilla-xformers" + double_z: true + z_channels: 4 + resolution: 256 + in_channels: 3 + out_ch: 3 + ch: 128 + ch_mult: + - 1 + - 2 + - 4 + - 4 + num_res_blocks: 2 + attn_resolutions: [] + dropout: 0.0 + lossconfig: + target: torch.nn.Identity + + cond_stage_config: + target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder + params: + freeze: True + layer: "penultimate" diff --git a/models/configs/v2-inference-v_fp32.yaml b/models/configs/v2-inference-v_fp32.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d5c9b9cb29ca162ade44a7c922f59e75d7d57813 --- /dev/null +++ b/models/configs/v2-inference-v_fp32.yaml @@ -0,0 +1,68 @@ +model: + base_learning_rate: 1.0e-4 + target: ldm.models.diffusion.ddpm.LatentDiffusion + params: + parameterization: "v" + linear_start: 0.00085 + linear_end: 0.0120 + num_timesteps_cond: 1 + log_every_t: 200 + timesteps: 1000 + first_stage_key: "jpg" + cond_stage_key: "txt" + image_size: 64 + channels: 4 + cond_stage_trainable: false + conditioning_key: crossattn + monitor: val/loss_simple_ema + scale_factor: 0.18215 + use_ema: False # we set this to false because this is an inference only config + + unet_config: + target: ldm.modules.diffusionmodules.openaimodel.UNetModel + params: + use_checkpoint: True + use_fp16: False + image_size: 32 # unused + in_channels: 4 + out_channels: 4 + model_channels: 320 + attention_resolutions: [ 4, 2, 1 ] + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 4 ] + num_head_channels: 64 # need to fix for flash-attn + use_spatial_transformer: True + use_linear_in_transformer: True + transformer_depth: 1 + context_dim: 1024 + legacy: False + + first_stage_config: + target: ldm.models.autoencoder.AutoencoderKL + params: + embed_dim: 4 + monitor: val/rec_loss + ddconfig: + #attn_type: "vanilla-xformers" + double_z: true + z_channels: 4 + resolution: 256 + in_channels: 3 + out_ch: 3 + ch: 128 + ch_mult: + - 1 + - 2 + - 4 + - 4 + num_res_blocks: 2 + attn_resolutions: [] + dropout: 0.0 + lossconfig: + target: torch.nn.Identity + + cond_stage_config: + target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder + params: + freeze: True + layer: "penultimate" diff --git a/models/configs/v2-inference.yaml b/models/configs/v2-inference.yaml new file mode 100644 index 0000000000000000000000000000000000000000..152c4f3c2b36c3b246a9cb10eb8166134b0d2e1c --- /dev/null +++ b/models/configs/v2-inference.yaml @@ -0,0 +1,67 @@ +model: + base_learning_rate: 1.0e-4 + target: ldm.models.diffusion.ddpm.LatentDiffusion + params: + linear_start: 0.00085 + linear_end: 0.0120 + num_timesteps_cond: 1 + log_every_t: 200 + timesteps: 1000 + first_stage_key: "jpg" + cond_stage_key: "txt" + image_size: 64 + channels: 4 + cond_stage_trainable: false + conditioning_key: crossattn + monitor: val/loss_simple_ema + scale_factor: 0.18215 + use_ema: False # we set this to false because this is an inference only config + + unet_config: + target: ldm.modules.diffusionmodules.openaimodel.UNetModel + params: + use_checkpoint: True + use_fp16: True + image_size: 32 # unused + in_channels: 4 + out_channels: 4 + model_channels: 320 + attention_resolutions: [ 4, 2, 1 ] + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 4 ] + num_head_channels: 64 # need to fix for flash-attn + use_spatial_transformer: True + use_linear_in_transformer: True + transformer_depth: 1 + context_dim: 1024 + legacy: False + + first_stage_config: + target: ldm.models.autoencoder.AutoencoderKL + params: + embed_dim: 4 + monitor: val/rec_loss + ddconfig: + #attn_type: "vanilla-xformers" + double_z: true + z_channels: 4 + resolution: 256 + in_channels: 3 + out_ch: 3 + ch: 128 + ch_mult: + - 1 + - 2 + - 4 + - 4 + num_res_blocks: 2 + attn_resolutions: [] + dropout: 0.0 + lossconfig: + target: torch.nn.Identity + + cond_stage_config: + target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder + params: + freeze: True + layer: "penultimate" diff --git a/models/configs/v2-inference_fp32.yaml b/models/configs/v2-inference_fp32.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0d03231f3f2c2e8ef8fbe0d781e5f3d65409ef3a --- /dev/null +++ b/models/configs/v2-inference_fp32.yaml @@ -0,0 +1,67 @@ +model: + base_learning_rate: 1.0e-4 + target: ldm.models.diffusion.ddpm.LatentDiffusion + params: + linear_start: 0.00085 + linear_end: 0.0120 + num_timesteps_cond: 1 + log_every_t: 200 + timesteps: 1000 + first_stage_key: "jpg" + cond_stage_key: "txt" + image_size: 64 + channels: 4 + cond_stage_trainable: false + conditioning_key: crossattn + monitor: val/loss_simple_ema + scale_factor: 0.18215 + use_ema: False # we set this to false because this is an inference only config + + unet_config: + target: ldm.modules.diffusionmodules.openaimodel.UNetModel + params: + use_checkpoint: True + use_fp16: False + image_size: 32 # unused + in_channels: 4 + out_channels: 4 + model_channels: 320 + attention_resolutions: [ 4, 2, 1 ] + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 4 ] + num_head_channels: 64 # need to fix for flash-attn + use_spatial_transformer: True + use_linear_in_transformer: True + transformer_depth: 1 + context_dim: 1024 + legacy: False + + first_stage_config: + target: ldm.models.autoencoder.AutoencoderKL + params: + embed_dim: 4 + monitor: val/rec_loss + ddconfig: + #attn_type: "vanilla-xformers" + double_z: true + z_channels: 4 + resolution: 256 + in_channels: 3 + out_ch: 3 + ch: 128 + ch_mult: + - 1 + - 2 + - 4 + - 4 + num_res_blocks: 2 + attn_resolutions: [] + dropout: 0.0 + lossconfig: + target: torch.nn.Identity + + cond_stage_config: + target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder + params: + freeze: True + layer: "penultimate" diff --git a/models/configs/v2-inpainting-inference.yaml b/models/configs/v2-inpainting-inference.yaml new file mode 100644 index 0000000000000000000000000000000000000000..32a9471d71b828c51bcbbabfe34c5f6c8282c803 --- /dev/null +++ b/models/configs/v2-inpainting-inference.yaml @@ -0,0 +1,158 @@ +model: + base_learning_rate: 5.0e-05 + target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion + params: + linear_start: 0.00085 + linear_end: 0.0120 + num_timesteps_cond: 1 + log_every_t: 200 + timesteps: 1000 + first_stage_key: "jpg" + cond_stage_key: "txt" + image_size: 64 + channels: 4 + cond_stage_trainable: false + conditioning_key: hybrid + scale_factor: 0.18215 + monitor: val/loss_simple_ema + finetune_keys: null + use_ema: False + + unet_config: + target: ldm.modules.diffusionmodules.openaimodel.UNetModel + params: + use_checkpoint: True + image_size: 32 # unused + in_channels: 9 + out_channels: 4 + model_channels: 320 + attention_resolutions: [ 4, 2, 1 ] + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 4 ] + num_head_channels: 64 # need to fix for flash-attn + use_spatial_transformer: True + use_linear_in_transformer: True + transformer_depth: 1 + context_dim: 1024 + legacy: False + + first_stage_config: + target: ldm.models.autoencoder.AutoencoderKL + params: + embed_dim: 4 + monitor: val/rec_loss + ddconfig: + #attn_type: "vanilla-xformers" + double_z: true + z_channels: 4 + resolution: 256 + in_channels: 3 + out_ch: 3 + ch: 128 + ch_mult: + - 1 + - 2 + - 4 + - 4 + num_res_blocks: 2 + attn_resolutions: [ ] + dropout: 0.0 + lossconfig: + target: torch.nn.Identity + + cond_stage_config: + target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder + params: + freeze: True + layer: "penultimate" + + +data: + target: ldm.data.laion.WebDataModuleFromConfig + params: + tar_base: null # for concat as in LAION-A + p_unsafe_threshold: 0.1 + filter_word_list: "data/filters.yaml" + max_pwatermark: 0.45 + batch_size: 8 + num_workers: 6 + multinode: True + min_size: 512 + train: + shards: + - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-0/{00000..18699}.tar -" + - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-1/{00000..18699}.tar -" + - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-2/{00000..18699}.tar -" + - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-3/{00000..18699}.tar -" + - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-4/{00000..18699}.tar -" #{00000-94333}.tar" + shuffle: 10000 + image_key: jpg + image_transforms: + - target: torchvision.transforms.Resize + params: + size: 512 + interpolation: 3 + - target: torchvision.transforms.RandomCrop + params: + size: 512 + postprocess: + target: ldm.data.laion.AddMask + params: + mode: "512train-large" + p_drop: 0.25 + # NOTE use enough shards to avoid empty validation loops in workers + validation: + shards: + - "pipe:aws s3 cp s3://deep-floyd-s3/datasets/laion_cleaned-part5/{93001..94333}.tar - " + shuffle: 0 + image_key: jpg + image_transforms: + - target: torchvision.transforms.Resize + params: + size: 512 + interpolation: 3 + - target: torchvision.transforms.CenterCrop + params: + size: 512 + postprocess: + target: ldm.data.laion.AddMask + params: + mode: "512train-large" + p_drop: 0.25 + +lightning: + find_unused_parameters: True + modelcheckpoint: + params: + every_n_train_steps: 5000 + + callbacks: + metrics_over_trainsteps_checkpoint: + params: + every_n_train_steps: 10000 + + image_logger: + target: main.ImageLogger + params: + enable_autocast: False + disabled: False + batch_frequency: 1000 + max_images: 4 + increase_log_steps: False + log_first_step: False + log_images_kwargs: + use_ema_scope: False + inpaint: False + plot_progressive_rows: False + plot_diffusion_rows: False + N: 4 + unconditional_guidance_scale: 5.0 + unconditional_guidance_label: [""] + ddim_steps: 50 # todo check these out for depth2img, + ddim_eta: 0.0 # todo check these out for depth2img, + + trainer: + benchmark: True + val_check_interval: 5000000 + num_sanity_val_steps: 0 + accumulate_grad_batches: 1 diff --git a/models/controlnet/put_controlnets_and_t2i_here b/models/controlnet/put_controlnets_and_t2i_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/diffusers/put_diffusers_models_here b/models/diffusers/put_diffusers_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/diffusion_models/MOXINGYIH.safetensors b/models/diffusion_models/MOXINGYIH.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de457d8edba716c3d1ebd53556ed531ad1e76853 --- /dev/null +++ b/models/diffusion_models/MOXINGYIH.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10125ab5c86167d3f3d4836e52b5317d611b98a1603d075b9e1f568843968d84 +size 15003000250 diff --git a/models/diffusion_models/MOXINGYIL.safetensors b/models/diffusion_models/MOXINGYIL.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..39d7442d8c713cf6e3d13d8987601d70473b1cbe --- /dev/null +++ b/models/diffusion_models/MOXINGYIL.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90444bc6fb98d693b8afc18a13a7a5c35f751c2b71252d73438ed0649633057b +size 15003000250 diff --git a/models/diffusion_models/put_diffusion_model_files_here b/models/diffusion_models/put_diffusion_model_files_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/embeddings/put_embeddings_or_textual_inversion_concepts_here b/models/embeddings/put_embeddings_or_textual_inversion_concepts_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/gligen/put_gligen_models_here b/models/gligen/put_gligen_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/hypernetworks/put_hypernetworks_here b/models/hypernetworks/put_hypernetworks_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/latent_upscale_models/put_latent_upscale_models_here b/models/latent_upscale_models/put_latent_upscale_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/loras/NSFWH.safetensors b/models/loras/NSFWH.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1e51801a0aa624380e22521e732d0f8ca8dce5f --- /dev/null +++ b/models/loras/NSFWH.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34e2144d3cd65360f97d09ccbe03e1c39a096df6c9234af5fe3899d1b63cda39 +size 613516752 diff --git a/models/loras/NSFWL.safetensors b/models/loras/NSFWL.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f9aeee78e070b8a9206127c7fcd5778e6479fcbf --- /dev/null +++ b/models/loras/NSFWL.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b783742f4d5fd63a0223ae1d5bf64fc995a6b408480ac2a00528ae0d4146db +size 613516752 diff --git a/models/loras/WAN/MOXINGSIH.safetensors b/models/loras/WAN/MOXINGSIH.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db0280384ba0f24bc48eda048cd2efb3198fbf85 --- /dev/null +++ b/models/loras/WAN/MOXINGSIH.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f9697628913df51e1a6c0cd85ac4acd1ce6ac30525d2a385245fdd3d9cb3e2 +size 858457300 diff --git a/models/loras/WAN/MOXINGSIL.safetensors b/models/loras/WAN/MOXINGSIL.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d7009e756086e789d5734e5e037a6c720272d11c --- /dev/null +++ b/models/loras/WAN/MOXINGSIL.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e64ba89881720c4fc7db898a3976472a9c5e26fe3973e7b0760c8f8c7fb4ca9d +size 858457436 diff --git a/models/loras/WAN/MOXINGWU.safetensors b/models/loras/WAN/MOXINGWU.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce8dfe3127d8fd1080e3b1e8fb37793b84ba0245 --- /dev/null +++ b/models/loras/WAN/MOXINGWU.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f974aced60f1d833eca0f5d6851346fbb6eacc307c6371555b565f5617fe3859 +size 2923503944 diff --git a/models/loras/put_loras_here b/models/loras/put_loras_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git "a/models/loras/ru\344\272\244H.safetensors" "b/models/loras/ru\344\272\244H.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..67f970e00f8af36f0267dc9c7cdbd302730aa0ee --- /dev/null +++ "b/models/loras/ru\344\272\244H.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da831189ea88eb70ace1ac45ddc91b6e726799088af2b17ecd5f11dc9c86ab81 +size 306847624 diff --git "a/models/loras/ru\344\272\244L.safetensors" "b/models/loras/ru\344\272\244L.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..ec8c9047cbdeb01882532cd44c2457fbce569293 --- /dev/null +++ "b/models/loras/ru\344\272\244L.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a01762b11041709ce47cf502265c03b090923e6787659b89d1d8af502d19f65 +size 306847624 diff --git "a/models/loras/\344\270\200\344\275\223\345\214\226NSFWH.safetensors" "b/models/loras/\344\270\200\344\275\223\345\214\226NSFWH.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..5055f094efac1e9d0be97c3f94032ddb1873229e --- /dev/null +++ "b/models/loras/\344\270\200\344\275\223\345\214\226NSFWH.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9931756c202bd8d4946c0d163c1269231a6352b51bb4235f6a19894c9ad8c68 +size 306807976 diff --git "a/models/loras/\344\270\200\344\275\223\345\214\226NSFWL.safetensors" "b/models/loras/\344\270\200\344\275\223\345\214\226NSFWL.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..92d410ed4c7570c7f031daa003927660be7cd43e --- /dev/null +++ "b/models/loras/\344\270\200\344\275\223\345\214\226NSFWL.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:066ee4bfafb685c85f08174c8283cd11bc6d36f4845347f20d633ab44581601f +size 306807976 diff --git "a/models/loras/\344\274\240\346\225\231\345\243\253H.safetensors" "b/models/loras/\344\274\240\346\225\231\345\243\253H.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..28df96550cc16e0c0589fe376f60b224bc9beecc --- /dev/null +++ "b/models/loras/\344\274\240\346\225\231\345\243\253H.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e3e77a9ba98144429315db1720e074b0626646d86e5d48d37042e4a30d1bf1f +size 306849616 diff --git "a/models/loras/\344\274\240\346\225\231\345\243\253L.safetensors" "b/models/loras/\344\274\240\346\225\231\345\243\253L.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..7128434290737f512ef8f8a5eaba2d63e0700cd4 --- /dev/null +++ "b/models/loras/\344\274\240\346\225\231\345\243\253L.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d93769809f8c8cd061e64e38df0ed36d71f5bcc6f7d6f3bfba39aed66cf1403 +size 306849608 diff --git "a/models/loras/\345\217\243H.safetensors" "b/models/loras/\345\217\243H.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..578d2c002d2110db087eafcb761928ebe56d827c --- /dev/null +++ "b/models/loras/\345\217\243H.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ef7e7d6a9e11881e07dccb97ec64c6cab245cf85a2b205ee8eafc02b3137953 +size 306847576 diff --git "a/models/loras/\345\217\243L.safetensors" "b/models/loras/\345\217\243L.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..221af37029fdded9355160b90e674ad97bca4c5e --- /dev/null +++ "b/models/loras/\345\217\243L.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce502822e9547e5288725da1993bf363bf431e3cda2a14fb7ae527811e649b4 +size 306847568 diff --git "a/models/loras/\345\217\243\351\230\264H.safetensors" "b/models/loras/\345\217\243\351\230\264H.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..8b7873616489c20857b69cd84c48d5de1a6aabdc --- /dev/null +++ "b/models/loras/\345\217\243\351\230\264H.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d8afeffb8d8a04a76b656ebd8c1ae43f0ebc66e68c08881f7c1b70b178c0d38 +size 306807976 diff --git "a/models/loras/\345\217\243\351\230\264L.safetensors" "b/models/loras/\345\217\243\351\230\264L.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..6bdcafef7a7baeb7d7415892f4dfd6d110b489f9 --- /dev/null +++ "b/models/loras/\345\217\243\351\230\264L.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8ce432a5f1220d4c2f6c26f5ad11bf009cfcd02f8e2d4932a59d0b1b6ff0b4d +size 306807976 diff --git "a/models/loras/\345\220\270\344\271\263\345\244\264H.safetensors" "b/models/loras/\345\220\270\344\271\263\345\244\264H.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..400bd9cd70792ad5fe3fc5cd27cbca2dd922fd9b --- /dev/null +++ "b/models/loras/\345\220\270\344\271\263\345\244\264H.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:902dd2d550598d56894e4efc979c875796e7d3a30f1e50910f1a19eee43bc468 +size 306807976 diff --git "a/models/loras/\345\220\270\344\271\263\345\244\264L.safetensors" "b/models/loras/\345\220\270\344\271\263\345\244\264L.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..f77186409727edfd9a9e38c8bb538e18d4c76cb4 --- /dev/null +++ "b/models/loras/\345\220\270\344\271\263\345\244\264L.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cddb57e34e3ed7cc472c7eace5e0dda385a74dc2386c8a826eea7e28fdfa8cd1 +size 306807976 diff --git "a/models/loras/\345\245\263\344\270\212ITH.safetensors" "b/models/loras/\345\245\263\344\270\212ITH.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..25c809e8c13ad7c2c91fa6565e7124272570b8f2 --- /dev/null +++ "b/models/loras/\345\245\263\344\270\212ITH.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e39e4567ed9b5793321313bf0d74dc1a5c65ae98ee479072e78a7aae91d02f8e +size 613516752 diff --git "a/models/loras/\345\245\263\344\270\212ITL.safetensors" "b/models/loras/\345\245\263\344\270\212ITL.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..70c3d9fd709a632b257e52725e30765fa9365e46 --- /dev/null +++ "b/models/loras/\345\245\263\344\270\212ITL.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445c3de529557c1299fdf043d1c804ae7138be56cf6a0e20537cee6bba7a8e02 +size 613516752 diff --git "a/models/loras/\345\245\263\350\207\252\346\205\260H.safetensors" "b/models/loras/\345\245\263\350\207\252\346\205\260H.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..7514c1ba6f404dc11f6265ed1420229753023a72 --- /dev/null +++ "b/models/loras/\345\245\263\350\207\252\346\205\260H.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbfec14d2b71d3162329e29fded9b1ec76218f64bb82e89d4a0b68d508f7b728 +size 306807976 diff --git "a/models/loras/\345\245\263\350\207\252\346\205\260L.safetensors" "b/models/loras/\345\245\263\350\207\252\346\205\260L.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..16be45b47adbfc8b2bc9de67bba998abeb591f25 --- /dev/null +++ "b/models/loras/\345\245\263\350\207\252\346\205\260L.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:143f070903afc9b9fc2a13358aeada767e715a5ade996b5b4904127e5872471c +size 306807976 diff --git "a/models/loras/\345\256\214\347\276\216\351\230\264\346\210\267.safetensors" "b/models/loras/\345\256\214\347\276\216\351\230\264\346\210\267.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..edac2aa42a776b1aef48b317a46a71ba63387e20 --- /dev/null +++ "b/models/loras/\345\256\214\347\276\216\351\230\264\346\210\267.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:379c267ca9e6021bde9763c74a76117335181b189edbcd06e29acf1d16f6af10 +size 306807976 diff --git "a/models/loras/\345\260\204\347\262\276H.safetensors" "b/models/loras/\345\260\204\347\262\276H.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..8a2c50717c50115b43917f11f3d6d3e3e004e2b5 --- /dev/null +++ "b/models/loras/\345\260\204\347\262\276H.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a68ee10bb0f3162bf947a892591dfc65a111d7e85c3f73ff6db24887b79a0b05 +size 319116504 diff --git "a/models/loras/\345\260\204\347\262\276L.safetensors" "b/models/loras/\345\260\204\347\262\276L.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..2fc5ed33bf35375d4e19d92795377008302cd3d9 --- /dev/null +++ "b/models/loras/\345\260\204\347\262\276L.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:683d6a84430b7f1c7aa1d24a7b74981fe4bdb233a06006f0f0f613e61ccd483e +size 306807976 diff --git "a/models/loras/\346\211\213\345\212\240kouH.safetensors" "b/models/loras/\346\211\213\345\212\240kouH.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..7fa1084bc2b11b47e606e1b36140b51510fbea68 --- /dev/null +++ "b/models/loras/\346\211\213\345\212\240kouH.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0794f26ab43a5bbb479ff21bd6ae1466ff4a3d6a0c21676ab34b832b82b875e0 +size 613516752 diff --git "a/models/loras/\346\211\213\345\212\240kouL.safetensors" "b/models/loras/\346\211\213\345\212\240kouL.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..3eb68cc5667ee42eae0bcf9e35d4dae186ebb141 --- /dev/null +++ "b/models/loras/\346\211\213\345\212\240kouL.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4371ed72fe9804257e69b56a37217bdab641b76a64208b07a75f5d716a25985d +size 613516752 diff --git "a/models/loras/\346\267\261\345\226\211H.safetensors" "b/models/loras/\346\267\261\345\226\211H.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..e1cf05b1929c60ddfb855cac1ef08680cfd0dfad --- /dev/null +++ "b/models/loras/\346\267\261\345\226\211H.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78f890e148b539caf61b89d83f411031ea0f1e34cf6807c61d39b5b28b6406f8 +size 306807976 diff --git "a/models/loras/\346\267\261\345\226\211L.safetensors" "b/models/loras/\346\267\261\345\226\211L.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..cd1e079969d3f79805fa7d82658f26da0578a2f8 --- /dev/null +++ "b/models/loras/\346\267\261\345\226\211L.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe91142668b2f09d429e86f5018001304202c491e79411f059e5bf59b03a36e0 +size 306807976 diff --git "a/models/loras/\347\273\210\346\236\201\346\267\261\345\226\211H.safetensors" "b/models/loras/\347\273\210\346\236\201\346\267\261\345\226\211H.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..d36c11a5c01e22135db521b7517361569d403f03 --- /dev/null +++ "b/models/loras/\347\273\210\346\236\201\346\267\261\345\226\211H.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b04aed102ffc4bbba7ec9d52eece2507d33b6574838684731bbc47842004a763 +size 306808408 diff --git "a/models/loras/\347\273\210\346\236\201\346\267\261\345\226\211L.safetensors" "b/models/loras/\347\273\210\346\236\201\346\267\261\345\226\211L.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..33e0fd6da2ccb8512c6e1d25cc06c70560569a96 --- /dev/null +++ "b/models/loras/\347\273\210\346\236\201\346\267\261\345\226\211L.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b14007d6a7c8ca88e33c74de087c4d900f66731990339612f32d9e272b354d6 +size 306807976 diff --git "a/models/loras/\350\242\253\346\217\211\350\203\270H.safetensors" "b/models/loras/\350\242\253\346\217\211\350\203\270H.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..b5b2876795ef8372497c9ad80a9eaef05970347f --- /dev/null +++ "b/models/loras/\350\242\253\346\217\211\350\203\270H.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ad6b18be9a8333c5a312167aac8aa223a395ebf4a1493ed2f3213d17db2a58d +size 306808408 diff --git "a/models/loras/\350\242\253\346\217\211\350\203\270L.safetensors" "b/models/loras/\350\242\253\346\217\211\350\203\270L.safetensors" new file mode 100644 index 0000000000000000000000000000000000000000..d36c11a5c01e22135db521b7517361569d403f03 --- /dev/null +++ "b/models/loras/\350\242\253\346\217\211\350\203\270L.safetensors" @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b04aed102ffc4bbba7ec9d52eece2507d33b6574838684731bbc47842004a763 +size 306808408 diff --git a/models/model_patches/put_model_patches_here b/models/model_patches/put_model_patches_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/photomaker/put_photomaker_models_here b/models/photomaker/put_photomaker_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/style_models/put_t2i_style_model_here b/models/style_models/put_t2i_style_model_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/text_encoders/MOXINGER.safetensors b/models/text_encoders/MOXINGER.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c8f3c98145fac6dc21d3883a6ff30ee13140ba94 --- /dev/null +++ b/models/text_encoders/MOXINGER.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a484bb9739a8d4020ca6f072b5b7329cf13e352b06985497c1f7f81ea98a45c5 +size 6735887993 diff --git a/models/text_encoders/put_text_encoder_files_here b/models/text_encoders/put_text_encoder_files_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/unet/put_unet_files_here b/models/unet/put_unet_files_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/upscale_models/OmniSR_X2_DIV2K.safetensors b/models/upscale_models/OmniSR_X2_DIV2K.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a5b74ac4bc9a45215a2741ed1e9b90c7790d0468 --- /dev/null +++ b/models/upscale_models/OmniSR_X2_DIV2K.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79408fc23203bf161faa957c4a602cc40521ed2235a72d976bd9d375e6644611 +size 1655992 diff --git a/models/upscale_models/put_esrgan_and_other_upscale_models_here b/models/upscale_models/put_esrgan_and_other_upscale_models_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/vae/MOXINGSAN.safetensors b/models/vae/MOXINGSAN.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5ff32b52dac309662138ca42604696d34eaad7b8 --- /dev/null +++ b/models/vae/MOXINGSAN.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fc39d31359a4b0a64f55876d8ff7fa8d780956ae2cb13463b0223e15148976b +size 253815318 diff --git a/models/vae/put_vae_here b/models/vae/put_vae_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/models/vae_approx/put_taesd_encoder_pth_and_taesd_decoder_pth_here b/models/vae_approx/put_taesd_encoder_pth_and_taesd_decoder_pth_here new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391